What is lilypond-mcp CLAUDE.md?

Project instructions for lilypond-mcp, a service that turns LilyPond music-notation files into usable PDF, EPS, SVG, or PNG assets.

They guide development, testing, branching, pull requests, and release documentation for lilypond-mcp.

They document the repository's working rules and technical traps, including how releases and the music-notation engine must be handled.

How wspringer/lilypond-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to wspringer/lilypond-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/wspringer/lilypond-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/wspringer/lilypond-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/wspringer/lilypond-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/wspringer/lilypond-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/wspringer/lilypond-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wspringer/lilypond-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/wspringer/lilypond-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wspringer/lilypond-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 790 This file is loaded in full into every session.

When invoked 790 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00790	$0.00790
Opus 5	$0.00395	$0.00395
Sonnet 5	$0.00158	$0.00158
Haiku 4.5	$0.00079	$0.00079

Measured 8d ago against content hash 430e1bac0fdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

lilypond-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lilypond-mcp

MCP server that engraves LilyPond sources into placeable assets (PDF, EPS, SVG, PNG) with a WebAssembly build of LilyPond, fetched from lilypond-wasi releases and pinned in engine.json; an installed LilyPond is never used. See README.md for the user-facing story and LICENSING.md for why this repo is MIT around a GPL engine.

Working practices

Feature branches + PRs, never direct pushes to main. Branch protection enforces this; the test check is required.
Document every user-facing change with a change file (Knope's changesets): run knope document-change, or write .changeset/<slug>.md by hand:
```
---
default: minor
---

#### One-line summary for the changelog

Optional detail paragraphs, written for npm users.
```
Bump types: major (breaking), minor (feature), patch (fix). Change files are the only source of release semantics ([changes] ignore_conventional_commits = true in knope.toml): commit subjects never bump versions or write changelog entries. A user-facing change without a change file silently ships undocumented — don't. Conventional PR titles (fix:, feat:, ci:) remain as history hygiene, nothing more. A PR that changes nothing for npm users (CI, dev config, comments) gets the not user facing label instead, which skips the bot's check.
Releases: the Knope bot keeps a release PR open; merging it tags, writes the changelog, and release.yml publishes to npm via trusted publishing (OIDC). Never npm publish by hand.

Gotchas that cost real time

node:wasi fast calls corrupt memory from Node 22.21.1 (the WasiFunction fast-call signature backport, nodejs/node#59600): the engine segfaults during Guile startup, all platforms, with empty stderr. The worker always runs with --no-turbo-fast-api-calls, which sidesteps it — never remove that flag without re-bisecting. (Node 24 is unaffected either way.)
PRs opened with GITHUB_TOKEN (e.g. by trail-engine.yml) don't trigger workflows, so required checks never run on them. Nudge with an empty commit pushed by a real user, or set a GH_PAT secret (the workflow already prefers it).
InDesign needs the PDF (fonts subsetted, all boxes stamped) — never hand it LilyPond EPS.
LilyPond mangles single-component -I dirs (/inc never resolves, /deep/inc does — its File_name parser). Every guest include path is two components: /src/dir for the source's own directory, /include/N for include_dirs.

Read the full file on GitHub · 67 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 67 lines · 790 tokens per session scan A 430e1bac0fdd

Subscribe to this mod's changes

lilypond-mcp CLAUDE.md is an instructions file published in the GitHub repository wspringer/lilypond-mcp (0 stars, last pushed today), licensed MIT. It adds 790 tokens to every session, about $0.0040 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

lilypond-mcp: Instructions file for Claude Code